Background: Tracking of dietary intake is key to enhancing weight loss. Mobile apps may be useful for tracking food intake and can provide feedback about calories and nutritional value. Recent technological developments have enabled image recognition to identify foods and track food intake.
Objective: We aimed to determine the effectiveness of using photography as a feature of a smartphone weight loss app to track food intake in adults who were overweight or obese.
Methods: We analyzed data from individuals (age, 18-65 years; body mass index≥25 kg/m2; ≥4 days of logged food intake; and ≥2 weigh-ins) who used a mobile-based weight loss app. In a retrospective study, we compared those who used the photo feature (n=9871) and those who did not use the feature (n=113,916). Linear regression analyses were used to assess use of the photo feature in relation to percent weight loss.
Results: Weight loss was greater in the group using the photo feature (Δ=0.14%; 95% CI 0.06-0.22; P<.001). The photo feature group used the weight loss app for a longer duration (+3.5 days; 95% CI 2.61-4.37; P<.001) and logged their food intake on more days (+6.1 days; 95% CI 5.40-6.77; P<.001) than the nonusers. Mediation analysis showed that the weight loss effect was absent when controlling for either duration or number of logged days in the program.
Conclusions: This study was the first to examine the effect of a food photo feature to track food intake on weight loss in a free-living setting. Use of photo recognition was associated with greater weight loss, which was mediated by the duration of app use and number of logged days in the program.
More than two-thirds of adults are considered to be overweight or obese in the United States . Individuals with obesity are at an increased risk of developing cardiovascular disease, type 2 diabetes, and hypertension and are at a greater risk of mortality [ , ]. Weight loss can reduce the severity of these comorbidities or help prevent them [ , ]. Lifestyle modifications including calorie restriction can be effective in reducing body weight in the short term, although such approaches are less successful in the long term: Only about 20% of overweight individuals were successful at long-term weight loss, defined as losing at least 10% of the initial body weight and maintaining the weight for at least 1 year [ ]. The current obesity epidemic has generated a large market for weight loss programs. Commercial weight loss programs offer various aids, including mobile apps that allow tracking of food intake.
The majority of the US adult population (77%) reported owning a smartphone device in 2018 . Tracking of food intake by using a mobile app can provide instant feedback about the calories and nutrients of the meal. Dietary self-monitoring is a key component in weight loss programs [ ], and frequency of self-monitoring is strongly correlated with weight loss [ , ]. Some studies have reported a modest, although significantly greater, weight loss associated with the use of mobile apps compared to more traditional methods such as pen and paper [ - ], whereas others have found no difference [ - ]. Meta-analyses and systematic reviews of the recent literature also report mixed results, partly due to variation in the inclusion criteria [ , ]. In one meta-analysis, Flores-Mateo et al [ ] reported significantly greater weight loss among people using mobile apps as compared to those using other methods, whereas Semper et al [ ] reported no significant difference in their meta-analysis.
Self-monitoring requires time and effort, and many find tracking of dietary intake tedious, which contributes to attrition . Obesity researchers and weight loss companies have attempted to improve the ease of tracking by offering new features. One such feature employs photography of food items to monitor dietary intake both in the clinical setting and everyday life [ - ]. Since the technology has only been developed recently, the literature on this subject is limited. However, a few studies have examined the effect of using photography to record food intake. A method developed by Martin et al [ ], called Remote Food Photography Method (RFPM), uses semiautomatic computer analysis performed by researchers to obtain nutritional value from food images submitted by users. However, due to technological limitations, this process needs to be overseen by trained professionals [ , ]. Recent studies using RFPM conducted in pregnant women and preschoolers with obesity found that this method was not accurate in estimating energy intake compared to doubly labeled water [ , ]. Doumit et al conducted a cross-over study in college students, mostly of normal weight, to examine the effects of recording food intake from memory or with the aid of cell phone photos on energy intake and food choices [ ]. They reported a nonsignificant trend for lower energy intake in the group using cell phone photos, suggesting increased awareness of food choice and portion size. The study did not assess weight change and was of a short duration, with 3 days for each assessment period. A retrospective cohort study examined factors related to the use of food photography with an app that promotes healthy eating [ ]. Active users (with 10 photos or more) had, on an average, used the app for longer and had higher healthy ratings per photo than nonactive users (1 photo) and semiactive users (2-9 photos). However, this study did not monitor weight change.
Recently, a new tool, Snap It™, became available that allows participants to take photos of their food, and through image recognition technology attempts to match the food item to a large food photo database . We investigated the effect of using a food image recognition feature as part of a mobile app for tracking food intake on weight loss. We hypothesized that the photo feature users would lose more weight than nonusers.
Lose It! is a free weight loss mobile app launched in 2008 by FitNow (Boston, MA), which allows users to record their daily food intake. Users enter their self-reported weight, height, gender, and age when they sign up. They choose their goal weight and the rate at which they would like to lose weight (0-2 lbs per week). The app allows users to record food intake and exercise, calculates calories consumed, and estimates calories expended. All users have a calculated calorie budget for the day and can see whether their intake was within their budget. Users can also choose to pay US $39.99 per year for the premium features, which offer meal and exercise planning, macronutrient tracking, and recipes. In November 2016, a new free feature was added to the app that utilizes a food image tool called Snap It, which recognizes food items and requests the user to confirm their meal items from a list of potential matching foods and to add estimated portion sizes. The feature became available to all users of the app, but only a fraction have used it. We investigated weight loss outcomes among those who used the app versus those who did not. The data were de-identified before they were provided to us by the company FitNow, which had no role in the development of the protocol, the interpretation of the data, or the preparation of the manuscript.
The Snap It photo feature is shown inand is available to all app users at no additional cost. The user takes a photo of food items and then obtains a list of food items that the software recognizes as potential matches. The user subsequently chooses the correct match and specifies the quantity consumed from the list. Thereafter, the calories and macronutrients are calculated and displayed.
We received the dataset from FitNow, Inc, which included 175,402 users who joined between November 1, 2016, and January 31, 2017. Data collection for this sample ended in April 2017 and included individuals who had logged food intake in the app for a minimum of 4 days; had at least two reported weigh-ins; had a date of birth between January 11, 1936, and April 21, 1999; and reported >3 feet in height and a body weight between 70 and 750 pounds. The study was approved by the Touro College and University System Institutional Review Board (HSIRB# 1746E). We analyzed individuals who were overweight or obese, defined by a starting body mass index (BMI)≥25 kg/m2 , with a final BMI≥18 kg/m2 and age of 18-65 years. To exclude users with unrealistic data, we removed outliers outside the 99.7% CIs for height, starting weight, starting BMI, and %weight change. Only users who used an iPhone or an Android phone were included, thus excluding Web users, as the photo feature is not available on the LoseIt! website. Usage duration was calculated based on the number of days between the first and last reported weigh-ins, and the number of “logged days” was based on the number of days that intake was entered in the app. The groups were defined as photo feature users if they used the photo feature to log food intake for at least 1 or more days, and as nonusers if they did not use the photo feature at all. Only 7.8% (13,663/175,402) had used the photo feature, likely because the feature was new. We then excluded users who did not meet the inclusion-exclusion criteria or had missing or outlier data. We analyzed 123,787 users overall ( ), grouped by those who used the photo feature (n=9871) and those who did not use the feature (n=113,916). Among the photo feature users, we examined weight change in relation to the number of days the photo feature was used to log food intake.
We applied regression analysis using RStudio (version 1.0.14, RStudio Team, Boston, MA) to compare the %weight loss for the photo users and nonusers as well as duration in the program and number of logged days. We included the covariates, starting BMI, gender, age, premium status, and type of user operating system (Android or iPhone). We then reanalyzed the %weight loss data and controlled for duration and number of logged days. Chi-squared tests and t tests were used for baseline characteristics and comparisons between groups. Results were considered significant if the P value was ≤.05. The SD or 95% CI was used to represent the variance around the mean.
shows the composition of the study sample and the baseline characteristics of the participants, including age, starting weight, starting BMI, type of operating system (Android or iPhone), premium subscription status, and goal weight. Nonphoto feature users were younger, had a lower BMI and a lower body weight, used iPhones more often (vs Android), and paid for the premium version of the LoseIt! app less often than photo feature users.
|Characteristic||Nonusers (n=113,916)||Users (n=9871)||P value|
|Age (years), mean (SD)||36.1 (12.1)||36.5 (11.9)||<.001|
|Starting weight (kg), mean (SD)||93.6 (20.5)||94.0 (20.6)||.051|
|Starting body mass index (kg/m2), mean (SD)||32.7 (6.2)||33.1 (6.3)||<.001|
|Female, n (%)||83,150 (72.99)||7153 (72.46)||.26|
|Android, n (%)||28,041 (24.62)||3438 (34.83)||<.001|
|iPhone, n (%)||85,875 (75.38)||6433 (65.17)||<.001|
|Premium, n (%)||13,283 (11.66)||1834 (18.58)||<.001|
|Goal weight loss (kg), mean (SD)||8.7 (6.2)||8.9 (6.3)||.001|
Reported body weight decreased over time across the two groups, with greater weight loss in the photo feature group. The photo feature users lost 0.14% more (mean 3.42%; 95% CI 3.27-3.58) than the nonusers (mean 3.28%; 95% CI 3.24-3.32; P<.001), which translated to a 0.15 kg difference (photo feature users: mean weight loss=3.29 kg, 95% CI 3.14-3.45; nonusers: mean weight loss=3.14 kg, 95% CI 3.10-3.19). The difference in the %weight loss remained significant after adjusting for starting BMI, age, gender, user operating system, and premium status (P=.002), which were all significantly associated with the %weight loss. When adjusted for duration, photo feature use was not significantly associated with %weight loss (P=.40), and when adjusted for the number of logged days, the weight loss effect was reversed, where photo feature use was associated with an increase in body weight (+0.18 kg; P<.001). Duration and number of logged days were both significantly associated with %weight loss (r=0.33, P<.001 and r=0.46, P<.001, respectively). Collinearity between duration and number of logged days was not significant (variation inflation factor=1.37).
Within group analysis of photo feature users only showed that the number of days the photo feature was used was significantly associated with the %weight loss (P<.001). The difference was associated with 0.04% (95% CI 0.02-0.06) weight loss for every additional day of using the photo feature.
Of the 123,787 users analyzed, 15,117 (12.2%) were premium users and 1834 (12.1%) of the premium users used the photo feature. Premium users had a higher starting weight (96.4 kg; 95% CI 95.6-97.2) than nonpremium users (93.2 kg; 95% CI 93.0-93.4; P<.001). Premium users also lost more weight (mean 3.77 kg; 95% CI 3.60-3.93) than nonpremium users (mean 3.23 kg; 95% CI 3.19-3.27; P<.001). The difference remained significant even after adjusting for starting BMI, age, gender, and user operating system.
The photo feature group used the app for 3.5 days more than nonusers (photo feature users: mean 59.0 days, 95% CI 57.3-60.7; nonusers: mean 55.5 days, 95% CI 55.1-56.0; P<.001). The difference remained significant (3.2 days; P<.001) after adjusting for starting BMI, age, gender, user operating system, and premium status (P<.001).
Number of Logged Days
Photo users logged 6.1 more days than nonusers (users: mean 43.1 days, 95% CI 41.7-44.5; nonusers: mean 37.0 days, 95% CI 36.6-37.4). The difference remained significant (5.4 days, P<.001) after adjusting for starting BMI, age, gender, user operating system, and premium status.
As reported above, %weight loss was significantly associated with photo feature use (P<.001). Duration was also significantly associated with photo feature use (P<.001) and %weight loss (P<.001). When controlling for duration in the program, the effect of photo feature use on weight loss became nonsignificant (P=.40), indicating that duration was a mediator (). The number of logged days was also significantly associated with photo feature use (r=0.05; P<.001) and %weight loss (P<.001). The effect on %weight loss was reversed (ie, photo feature use was associated with an increase in body weight) when the number of logged days was controlled for (+0.18 kg; P<.001), indicating mediation ( ). Thus, both duration and number of logged days were significant mediators of the photo feature effect on %weight loss.
In this study, we analyzed data from 123,787 users of a weight loss app, which included an optional photo feature. Photo feature users lost significantly more weight than nonusers after adjusting for starting BMI, age, gender, user operating system, and premium status, which confirmed our hypothesis. Use of the photo feature might be less time consuming, more motivating, and more interactive than typing in food items.
Although statistically significant, the difference in weight loss between the groups was not clinically significant, indicating only a very small benefit of capturing food images by a phone camera. In addition, the photo feature users had more logged days and longer duration in the program, which may be due to enhanced motivation derived from taking photos, such as greater awareness of choice of food and portion size. Photographing food might also improve memory of the food eaten, which has been associated with reduced food intake . On the other hand, individuals who were more motivated initially may have opted to use the photo feature.
The weight loss effect was not significant when adjusted for duration in the program and was reversed when adjusted for number of logged days. Mediation analysis showed that the weight loss differences were mediated by duration and number of logged days. Since entering the number of logged days as a covariate reversed the direction of significance (ie, photo feature was associated with weight gain when adjusted for number of logged days), the number of logged days appears to more strongly mediate the effect than duration in use of the photo feature and weight loss. As previously shown, increased self-monitoring, such as that by recording food intake, correlates with weight loss . Thus, as the photo users remained in the program for a longer duration and logged more days, they spent more time recording their food intake.
An additional possible benefit to recording food intake by taking photos as compared to typing it into an app is that the photo is taken before the food is eaten, whereas typing in a food item is customarily done at end of the meal or end of the day, based on memory . Thus, taking a photo prompts the user to acknowledge the nutritional content of the food item before consuming it, which may have a greater influence on their choice of food and portion size.
The frequency of photo feature use, reflected by the number of days of use of the photo feature, was significantly associated with weight loss, indicating that the more the photo feature was used, the greater the amount of weight lost. The photo feature users’ adherence, reflected in the number of logged days, was also higher than that of nonusers, suggesting that either the use of the photo feature motivated the users to continue with the program or that the users were more motivated to start with and used this feature as an additional tool. The latter theory is also supported by the increase in the proportion of photo feature users that subscribed to the premium features. As reported above, increased frequency of app use is correlated with increased weight loss and better maintenance . Use of the photo feature was associated with increased weight loss, as hypothesized, possibly due to greater frequency of app use leading to a more successful outcome. This is the first study to examine the effect of a food image recognition app feature to track food intake on weight loss in a large cohort in a naturalistic, free-living setting.
There were several limitations, including limited demographic information, which did not include income and race. This study was also based on self-reported values of body weight and height. Additionally, the groups were self-selected and the numbers were uneven. In future studies, we would add a survey to gather demographic information and feedback on the ease of use and motivation to use the app with the photo feature. We observed a significant correlation between %weight loss and photo feature use, but this observational study does not allow determination of cause and effect. The next logical step would be a randomized controlled trial to help determine causal direction.
We showed that use of a photo feature as part of a weight loss app was associated with greater weight loss, an effect mediated by increased duration and more logged days.
We thank Lose It!, a component of FitNow, Inc. In particular, we thank Sarah Molhan for providing us with the dataset. We also thank Katie Chase Martin for assistance with submission of the protocol to the institutional review board. Funding was provided by the Obesity Society through the Weight Watchers Karen Miller-Kovach Research Grant to AG.
Conflicts of Interest
- Fryar C, Ogden C. National Institute of Diabetes and Digestive and Kidney Disease. Overweight & Obesity Statistics URL: https://www.niddk.nih.gov/health-information/health-statistics/overweight-obesity [accessed 2018-08-08] [WebCite Cache]
- Wang YC, McPherson K, Marsh T, Gortmaker SL, Brown M. Health and economic burden of the projected obesity trends in the USA and the UK. Lancet 2011 Aug 27;378(9793):815-825. [CrossRef] [Medline]
- Grieve E, Fenwick E, Yang H, Lean M. The disproportionate economic burden associated with severe and complicated obesity: a systematic review. Obes Rev 2013 Nov;14(11):883-894. [CrossRef] [Medline]
- Diabetes Prevention Program Research Group, Knowler WC, Fowler SE, Hamman RF, Christophi CA, Hoffman HJ, et al. 10-year follow-up of diabetes incidence and weight loss in the Diabetes Prevention Program Outcomes Study. Lancet 2009 Nov 14;374(9702):1677-1686 [FREE Full text] [CrossRef] [Medline]
- Wadden TA, Volger S, Sarwer DB, Vetter ML, Tsai AG, Berkowitz RI, et al. A two-year randomized trial of obesity treatment in primary care practice. N Engl J Med 2011 Nov 24;365(21):1969-1979 [FREE Full text] [CrossRef] [Medline]
- Wing RR, Phelan S. Long-term weight loss maintenance. Am J Clin Nutr 2005 Jul;82(1 Suppl):222S-225S [FREE Full text] [Medline]
- Pew Research Center: Internet & Technology. Mobile Fact Sheet URL: http://www.pewinternet.org/fact-sheet/mobile/ [accessed 2018-12-26] [WebCite Cache]
- Burke LE, Wang J, Sevick MA. Self-monitoring in weight loss: a systematic review of the literature. J Am Diet Assoc 2011 Jan;111(1):92-102 [FREE Full text] [CrossRef] [Medline]
- Wharton CM, Johnston CS, Cunningham BK, Sterner D. Dietary self-monitoring, but not dietary quality, improves with use of smartphone app technology in an 8-week weight loss trial. J Nutr Educ Behav 2014 Oct;46(5):440-444. [CrossRef] [Medline]
- Kruger J, Blanck HM, Gillespie C. Dietary and physical activity behaviors among adults successful at weight loss maintenance. Int J Behav Nutr Phys Act 2006 Jul 19;3:17 [FREE Full text] [CrossRef] [Medline]
- Linde JA, Jeffery RW, French SA, Pronk NP, Boyle RG. Self-weighing in weight gain prevention and weight loss trials. Ann Behav Med 2005 Dec;30(3):210-216. [CrossRef] [Medline]
- Chin SO, Keum C, Woo J, Park J, Choi HJ, Woo J, et al. Successful weight reduction and maintenance by using a smartphone application in those with overweight and obesity. Sci Rep 2016 Nov 07;6:34563 [FREE Full text] [CrossRef] [Medline]
- Goldstein DJ. The Management Of Eating Disorders And Obesity (nutrition And Health). Totowa, NJ: Humana Press; 2005.
- Allen JK, Stephens J, Dennison Himmelfarb CR, Stewart KJ, Hauck S. Randomized controlled pilot study testing use of smartphone technology for obesity treatment. J Obes 2013;2013:151597 [FREE Full text] [CrossRef] [Medline]
- Carter MC, Burley VJ, Nykjaer C, Cade JE. Adherence to a smartphone application for weight loss compared to website and paper diary: pilot randomized controlled trial. J Med Internet Res 2013;15(4):e32 [FREE Full text] [CrossRef] [Medline]
- Martin CK, Miller AC, Thomas DM, Champagne CM, Han H, Church T. Efficacy of SmartLoss, a smartphone-based weight loss intervention: results from a randomized controlled trial. Obesity (Silver Spring) 2015 May;23(5):935-942. [CrossRef] [Medline]
- Laing BY, Mangione CM, Tseng C, Leng M, Vaisberg E, Mahida M, et al. Effectiveness of a smartphone application for weight loss compared with usual care in overweight primary care patients: a randomized, controlled trial. Ann Intern Med 2014 Nov 18;161(10 Suppl):S5-12. [CrossRef] [Medline]
- Turner-McGrievy G, Tate D. Tweets, Apps, and Pods: Results of the 6-month Mobile Pounds Off Digitally (Mobile POD) randomized weight-loss intervention among adults. J Med Internet Res 2011;13(4):e120 [FREE Full text] [CrossRef] [Medline]
- Flores Mateo G, Granado-Font E, Ferré-Grau C, Montaña-Carreras X. Mobile Phone Apps to Promote Weight Loss and Increase Physical Activity: A Systematic Review and Meta-Analysis. J Med Internet Res 2015;17(11):e253 [FREE Full text] [CrossRef] [Medline]
- Semper HM, Povey R, Clark-Carter D. A systematic review of the effectiveness of smartphone applications that encourage dietary self-regulatory strategies for weight loss in overweight and obese adults. Obes Rev 2016 Sep;17(9):895-906. [CrossRef] [Medline]
- Eysenbach G. The law of attrition. J Med Internet Res 2005;7(1):e11 [FREE Full text] [CrossRef] [Medline]
- Winzer E, Luger M, Schindler K. Using digital photography in a clinical setting: a valid, accurate, and applicable method to assess food intake. Eur J Clin Nutr 2018 Jun;72(6):879-887. [CrossRef] [Medline]
- Zhang W, Yu Q, Siddiquie B, Divakaran A, Sawhney H. "Snap-n-Eat": Food Recognition and Nutrition Estimation on a Smartphone. J Diabetes Sci Technol 2015 May;9(3):525-533 [FREE Full text] [CrossRef] [Medline]
- Kong K, Zhang L, Huang L, Tao Y. Validity and practicability of smartphone-based photographic food records for estimating energy and nutrient intake. Asia Pac J Clin Nutr 2017 May;26(3):396-401 [FREE Full text] [CrossRef] [Medline]
- Hill C, Weir BW, Fuentes LW, Garcia-Alvarez A, Anouti DP, Cheskin LJ. Relationship Between Weekly Patterns of Caloric Intake and Reported Weight Loss Outcomes: Retrospective Cohort Study. JMIR Mhealth Uhealth 2018 Apr 16;6(4):e83 [FREE Full text] [CrossRef] [Medline]
- Martin CK, Han H, Coulon SM, Allen HR, Champagne CM, Anton SD. A novel method to remotely measure food intake of free-living individuals in real time: the remote food photography method. Br J Nutr 2009 Feb;101(3):446-456 [FREE Full text] [CrossRef] [Medline]
- Martin CK, Nicklas T, Gunturk B, Correa JB, Allen HR, Champagne C. Measuring food intake with digital photography. J Hum Nutr Diet 2014 Jan;27 Suppl 1:72-81 [FREE Full text] [CrossRef] [Medline]
- Martin CK, Correa JB, Han H, Allen HR, Rood JC, Champagne CM, et al. Validity of the Remote Food Photography Method (RFPM) for estimating energy and nutrient intake in near real-time. Obesity (Silver Spring) 2012 Apr;20(4):891-899 [FREE Full text] [CrossRef] [Medline]
- Most J, Vallo PM, Altazan AD, Gilmore LA, Sutton EF, Cain LE, et al. Food Photography Is Not an Accurate Measure of Energy Intake in Obese, Pregnant Women. J Nutr 2018 Apr 01;148(4):658-663. [CrossRef] [Medline]
- Nicklas T, Saab R, Islam NG, Wong W, Butte N, Schulin R, et al. Validity of the Remote Food Photography Method Against Doubly Labeled Water Among Minority Preschoolers. Obesity (Silver Spring) 2017 Dec;25(9):1633-1638 [FREE Full text] [CrossRef] [Medline]
- Doumit R, Long J, Kazandjian C, Gharibeh N, Karam L, Song H, et al. Effects of Recording Food Intake Using Cell Phone Camera Pictures on Energy Intake and Food Choice. Worldviews Evid Based Nurs 2016 Jun;13(3):216-223. [CrossRef] [Medline]
- Helander E, Kaipainen K, Korhonen I, Wansink B. Factors related to sustained use of a free mobile app for dietary self-monitoring with photography and peer feedback: retrospective cohort study. J Med Internet Res 2014;16(4):e109 [FREE Full text] [CrossRef] [Medline]
- Lose It!, FitNow, Inc. URL: https://www.loseit.com/snapit/ [accessed 2018-08-08] [WebCite Cache]
- World Health Organization. Obesity: preventing and managing the global epidemic: report of a WHO consultation URL: http://www.who.int/nutrition/publications/obesity/WHO_TRS_894/en/ [accessed 2018-08-08] [WebCite Cache]
- Brunstrom JM, Burn JF, Sell NR, Collingwood JM, Rogers PJ, Wilkinson LL, et al. Episodic memory and appetite regulation in humans. PLoS One 2012;7(12):e50707 [FREE Full text] [CrossRef] [Medline]
- Painter SL, Ahmed R, Hill JO, Kushner RF, Lindquist R, Brunning S, et al. What Matters in Weight Loss? An In-Depth Analysis of Self-Monitoring. J Med Internet Res 2017 May 12;19(5):e160 [FREE Full text] [CrossRef] [Medline]
- Burke LE, Sereika SM, Music E, Warziski M, Styn MA, Stone A. Using instrumented paper diaries to document self-monitoring patterns in weight loss. Contemp Clin Trials 2008 Mar;29(2):182-193 [FREE Full text] [CrossRef] [Medline]
- Burke LE, Warziski M, Starrett T, Choo J, Music E, Sereika S, et al. Self-monitoring dietary intake: current and future practices. J Ren Nutr 2005 Jul;15(3):281-290. [Medline]
|BMI: body mass index|
|RFPM: Remote Food Photography Method|
Edited by G Eysenbach; submitted 10.08.18; peer-reviewed by PH Lin, S Painter; comments to author 01.11.18; revised version received 25.12.18; accepted 21.01.19; published 29.05.19Copyright
©Daniela Ben Neriah, Allan Geliebter. Originally published in JMIR Mhealth and Uhealth (http://mhealth.jmir.org), 29.05.2019.
This is an open-access article distributed under the terms of the Creative Commons Attribution License (https://creativecommons.org/licenses/by/4.0/), which permits unrestricted use, distribution, and reproduction in any medium, provided the original work, first published in JMIR mhealth and uhealth, is properly cited. The complete bibliographic information, a link to the original publication on http://mhealth.jmir.org/, as well as this copyright and license information must be included.